Orchestrating Multi-Agent Systems for End-to-End Climate Data Science Workflows

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering


MPhil Thesis Defence


Title: "Orchestrating Multi-Agent Systems for End-to-End Climate Data Science 
Workflows"

By

Mr. Hyeonjae KIM


Abstract:

Climate science relies on automated workflows to transform comprehensive
research questions into data-driven insights over massive, heterogeneous
datasets distributed across multiple data repositories. With the rise of large
language models, automated workflow generation has become increasingly
feasible. However, existing approaches face significant challenges: generic
LLM agents lack domain-specific knowledge of climate data sources and analysis
conventions, while static scripting pipelines cannot adapt to diverse task
requirements or recover from execution failures. Consequently, existing
methods struggle to reliably complete complex, multi-step climate analysis
workflows.

The ClimateAgent framework is proposed to address these limitations through
specialized multi-agent orchestration. The architecture decomposes high-level
user questions into executable subtasks coordinated by a Plan-Agent, acquires
data via specialized Data-Agents that dynamically introspect API metadata to
synthesize valid download scripts, and completes analysis with a Coding-Agent
that generates Python code, visualizations, and scientific reports through
iterative self-correction. This design enables the system to maintain workflow
coherence across dependent steps while adapting to execution failures without
human intervention.

To enable systematic evaluation, the Climate-Agent-Bench-85 benchmark is
introduced, comprising real-world tasks spanning six climate phenomena:
atmospheric rivers, drought, extreme precipitation, heat waves, sea surface
temperature, and tropical cyclones. Experiments demonstrate that ClimateAgent
substantially outperforms strong baselines including GitHub Copilot and direct
GPT-5 synthesis across all evaluation dimensions, with particularly pronounced
improvements in tasks requiring multi-step reasoning, heterogeneous data
integration, and external tool coordination. These results establish that
structured multi-agent orchestration with domain-specific knowledge
integration and adaptive error recovery provides a viable path toward
reliable, end-to-end automation of complex scientific workflows.


Date:                   Monday, 24 November 2025

Time:                   4:00pm - 6:00pm

Venue:                  Room 5501
                        Lifts 25/26

Chairman:               Prof. Ke YI

Committee Members:      Dr. Binhang YUAN (Supervisor)
                        Dr. Mengqian LU (CIVL)